Control of dehumidification and regeneration

• Main Author: Liu, Yong
• Other Authors: Wang Youyi
• Format: Final Year Project
• Language: English
• Published: 2013
• Subjects: DRNTU::Engineering::Electrical and electronic engineering::Control and instrumentation::Control engineering
• Online Access: http://hdl.handle.net/10356/54307
• Institution: Nanyang Technological University

This thesis presents the back propagation network control for the liquid desiccant dehumidification system (LDDS) and the LDDS is one of the Heating, ventilation, and air conditioning (HVAC) systems to regulate the humidity, temperature, and air flow of the room with high energy efficiency. In the LDDS, there are numerous factors influencing the performance of the system. For building one model to control the system, the five main parameters are chosen, and the relative humidity of the output air is regarded as the target, and the four inputs are the absolute temperature of the output air, the flow rate, temperature, and density of the liquid desiccant solution. The back propagation network is a good tool for dealing with the nonlinear system and is proposed. First, 75% of the 300 groups of data are utilized to train and simulate to acquire a model by using the back propagation network. Then, 25% of the 300 groups of data are put into the built model to be controlled to obtain the predicted data. Lastly, the comparison of the raw data and the predicted data identifies the model. Besides, the fundamentals of back propagation also are discussed.